© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 217056
    Prev
    Next
    INDEX
    Explanations

    base

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Annotations
    0.47
    ட்சய
    0.40
    側
    0.39
     ter
    0.38
     moj
    0.38
     moja
    0.38
     poisoned
    0.38
     Omn
    0.37
    Mis
    0.37
    weise
    0.37
    POSITIVE LOGITS
    ABASE
    0.38
    BER
    0.38
    BAD
    0.37
    ⒉
    0.37
    enton
    0.37
     ца
    0.37
    井
    0.37
    onga
    0.36
     BES
    0.36
    ibase
    0.36
    Activations Density 0.009%

    No Known Activations